| | |
|---|
| | | rescale_line = line_item[3:(len(line_item) - 1)] |
|---|
| | | vars_list = list(rescale_line) |
|---|
| | | continue |
|---|
| | | import pdb;pdb.set_trace() |
|---|
| | | means = np.array(means_list).astype(np.float32) |
|---|
| | | vars = np.array(vars_list).astype(np.float32) |
|---|
| | | cmvn = np.array([means, vars]) |
|---|
| | |
|---|
| | | return feats_pad, feats_lens, lfr_splice_frame_idxs |
|---|
| | | |
|---|
| | | def forward( |
|---|
| | | self, input: torch.Tensor, input_lengths: torch.Tensor, cache: dict = {}, **kwargs |
|---|
| | | self, input: torch.Tensor, input_lengths: torch.Tensor, **kwargs |
|---|
| | | ): |
|---|
| | | is_final = kwargs.get("is_final", False) |
|---|
| | | reset = kwargs.get("reset", False) |
|---|
| | | if len(cache) == 0 or reset: |
|---|
| | | cache = kwargs.get("cache", {}) |
|---|
| | | if len(cache) == 0: |
|---|
| | | self.init_cache(cache) |
|---|
| | | |
|---|
| | | batch_size = input.shape[0] |
|---|
| | |
|---|
| | | feats = torch.stack(cache["lfr_splice_cache"]) |
|---|
| | | feats_lengths = torch.zeros(batch_size, dtype=torch.int) + feats.shape[1] |
|---|
| | | feats, feats_lengths, _ = self.forward_lfr_cmvn(feats, feats_lengths, is_final, cache=cache) |
|---|
| | | if is_final: |
|---|
| | | self.init_cache(cache) |
|---|
| | | # if is_final: |
|---|
| | | # self.init_cache(cache) |
|---|
| | | return feats, feats_lengths |
|---|
| | | |
|---|
| | | |
|---|
